#6 · Primary category: AI Cloud Platforms & PaaS
OpenSandbox
Secure, Fast, and Extensible Sandbox runtime for AI agents.
Project last updated:08/28/26
GitHub Stars
14.8K
Forks
1.3K
Contributors
106
License
Apache-2.0
Why we included this project
Running a coding or browser agent against your real infrastructure tends to end badly, which is why OpenSandbox exists as an isolation layer in between. It spins up throwaway sandboxes on Docker or Kubernetes and gives the agent a clean way to run commands, move files, and execute code without touching anything you actually depend on. The multi-language SDKs, the osb CLI, and an MCP server mean it plugs into agent stacks you already have instead of demanding a new framework. When workloads get heavier, the Kubernetes runtime handles distributed scheduling, and you can add gVisor or Kata as a stronger isolation boundary. If your agents need to run code or drive a browser in earnest, this spares you from building that safe execution backend from scratch.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
appwrite
Appwrite® - complete cloud infrastructure for your web, mobile and AI apps. Including Auth, Databases, Storage, Functions, Messaging, Hosting, Realtime and more
dokploy
Open Source Alternative to Vercel, Netlify and Heroku.
sealos
Deploy real projects from GitHub or your AI coding agent, then keep them running with AI-powered operations.
kubesphere
The container platform tailored for Kubernetes multi-cloud, datacenter, and edge management ⎈ 🖥 ☁️
coder
Secure environments for developers and their agents